© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 3-GEMMASCOPE-2-TRANSCODER-262K
    4. 124634
    Prev
    Next
    INDEX
    Explanations

    ftp server

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_3_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     comedor
    0.85
    з
    0.85
     fabriqu
    0.80
     financiera
    0.78
    тли
    0.75
    са
    0.72
     nourriture
    0.72
     norte
    0.72
     mezcl
    0.70
     degust
    0.70
    POSITIVE LOGITS
    ↵↵
    0.99
     and
    0.86
    f
    0.84
    V
    0.82
    and
    0.78
    ih
    0.75
    BS
    0.74
     have
    0.74
    K
    0.73
    ية
    0.73
    Activations Density 0.000%

    No Known Activations